Public/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-09-20 01:31:31 +02:00
Code Issues Packages Projects Releases Wiki Activity

llama : load MTP tensors only if they are really used (#26296)

Browse Source 
* llama : load MTP tensors only if they are really used

* llama : skip loading MTP (if not used) in remaining models that support MTP

---------

Co-authored-by: Stanisław Szymczyk <sszymczy@gmail.com>
This commit is contained in:
fairydreaming
2026-07-31 14:57:02 +02:00
committed by GitHub
parent 6f3c0a790b
commit 82dbc4f017
13 changed files with 65 additions and 40 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/llama-model-loader.h
+2
View File
@@ -79,6 +79,7 @@ struct llama_model_loader {
bool use_direct_io = false;
bool check_tensors;
bool no_alloc;
bool load_mtp;
llama_files files;
llama_ftype ftype;
@@ -129,6 +130,7 @@ struct llama_model_loader {
llama_load_mode load_mode,
bool check_tensors,
bool no_alloc,
bool load_mtp,
const llama_model_kv_override * param_overrides_p,
const llama_model_tensor_buft_override * param_tensor_buft_overrides_p);